Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key phrases concerning policy support and opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yi
    -0.16
    cek
    -0.16
    adge
    -0.15
     vow
    -0.15
    ALCHEMY
    -0.14
    ÙħاÙĨÛĮ
    -0.13
    vero
    -0.13
     xong
    -0.13
     вза
    -0.13
    963
    -0.13
    POSITIVE LOGITS
     idea
    0.22
     allowing
    0.22
     expansion
    0.21
     continued
    0.21
     increased
    0.21
     expanded
    0.20
     further
    0.19
    expanded
    0.19
     extending
    0.19
     continuation
    0.19
    Act Density 0.242%

    No Known Activations